agent-context

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.

All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine

Agent memory: long-term memory & agent memory handoff. Claude Code & Codex.

Autonomous Agents (LLMs) research papers. Updated Daily.

Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.

Git-native memory for coding agents. Repo memory before the diff.

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

Repo-native shared memory for AI coding agents.

Record meetings and dictation on your Mac. Everything becomes plain Markdown files that Claude, Codex, or any AI can search. Free, open source, 100% local transcription.

AI agent context layer for career-related tasks.

One shared graph for every AI assistant and device — memory and tasks, local-first, signed, auditable, direct P2P sync. MCP tools; no hosted account.

Experiential world memory to help AI when web search is not enough.

Context alignment, version controlled.

Google Drive for AI agents — share files with your team, share context across your agents. Open source, no server required.

Build system for AI coding-agent context. Generate deterministic, explainable context artifacts for Claude, Codex, Cursor, and MCP.

A community-driven specification for creating, validating, and versioning structured context for AI systems

CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo) plus a knowledge-graph layer — ats kg: facts from any source, human-ratified. Recommended engines: Graphiti (server), LadybugDB (embedded).

Mnemovela - Agent Cognition Runtime (typed memory, Git-like branches, hybrid retrieval, governed forgetting; embedded-first Python & Go). Open-source client SDKs (Python/TypeScript/Go), CLI, API docs, and prebuilt binaries for Mnemovela. Apache-2.0.

Local-first CLI to read, compare, and hand off sessions across Claude Code, Codex, Gemini, and Cursor agents. Checkpoints, cross-agent messaging, zero npm deps.